Sometimes, I take breaks in the middle of a session and end up losing the prompt cache which drives up the token usage a ton. Don't all the providers have different cache times and behavior? If one person takes 20 minutes between messages, some services will keep that cache while some won't. Is there a way to factor that in?
OpenRouter shows the cache hit rate and calculates an effective pricing per provider if you scroll down on the model page. Note that some providers run fp4 versions of models. DeepInfra often does this
It's easy to scrape the pricing; you have to do some leg work to estimate the token efficiency, which factors into the ultimate cost. Ideally you'd compare reasoning efficiency too; given them all the same task.
200 tasks/day × 8 steps
GPT 5.6 Sol: $522.06
Opus 5: $456.06
Opus 5 comes out to be cheaper than Sol!
How do you calculate the effect of caching?
Sometimes, I take breaks in the middle of a session and end up losing the prompt cache which drives up the token usage a ton. Don't all the providers have different cache times and behavior? If one person takes 20 minutes between messages, some services will keep that cache while some won't. Is there a way to factor that in?
OpenRouter shows the cache hit rate and calculates an effective pricing per provider if you scroll down on the model page. Note that some providers run fp4 versions of models. DeepInfra often does this
It's easy to scrape the pricing; you have to do some leg work to estimate the token efficiency, which factors into the ultimate cost. Ideally you'd compare reasoning efficiency too; given them all the same task.